interests: Object Recognition and Categorization in Computer Vision, especially in combination with 3D Estimation and Tracking; Top-down Segmentation; Machine Learning. Education: Dr. Sc. techn.ETH Zurich
Computer Graphics 2009 best paper award (for our 3dRR-09 paper) 2009: Best Paper Award, 2nd International IEEE Workshop on 3D Representation for Recognition (3dRR-09), Kyoto, Japan, 2009 2003 - 2005: Support [...] connection with ICCV'13. I will be co-organizing the 4th International IEEE Workshop on 3D Representation and Recognition ( 3dRR-13 ), collocated with ICCV'13, together with Min Sun (University of Washington) [...] 2013: CVPR 2013 Outstanding Reviewer Award 2011: Best Paper Award, 3rd International IEEE Workshop on 3D Representation for Recognition (3dRR-11), Barcelona, Spain, 2011 2011: CVPR 2011 Best Reviewer Award
Qiu (Master Thesis) Sikandar Amin (PhD Student in Munich) Anna Senina (Intern, now PhD Student) Hessameddin Alibabaie (Intern) Reza Bahmanyar (Master Thesis, now PhD Student @ DLR ) Wandi Susanto (Master) [...] Dataset MPII Cooking Composite Activities MPII Multi-Kinect Dataset Multi-view Pictorial Structures for 3D Human Pose Estimation Semantic Relatedness for Knowledge Transfer Publications Please see my Google
Former Members Xucong Zhang Xucong Zhang (PhD Student) Personal Information Research Interests Computer Vision Human Computer Interaction Education 2010.9-2013.3: M.Sc. Beihang University, Beijing, China
functionalities of image and video understanding such as 3D object class recognition or 3D people detection and tracking. We also look at the problem of 3D scene understanding of traffic scenes as a case study [...] thesis in the field of robotics in Grenoble, France, where he also obtained the "diplome d'etudes approfondies d'informatique". In 1994 he worked in the field of multi-modal human-computer interfaces at [...] with the large-scale nature of current and future multimodal databases and sensor-streams. Education PhD: Docteur de l'Institut Polytechnique de Grenoble, France, 1997 MSc's: Diplom-Informatiker, University
the bag of features approach. Table 1. Results on CIFAR-10. Table 2. Results on CIFAR-100. Figure 3. Visual comparison between filters. Coates represents a traditional (hand-designed) spatial pooling [...] for Visual Recognition Recognizing Materials from Virtual Examples MPII Multi-Kinect Dataset Teaching 3D Geometry to Deformable Part Models Image Warping For Face Recognition Addressing scalability in object
Structures for 3D Human Pose Estimation Multi-view Pictorial Structures for 3D Human Pose Estimation We propose a multi-view pictorial structures model that builds on recent advances in 2D pose estimation [...] Jog, Box S2 - Walking, Jog S3 - Walking, Jog Ground truth annotations (4 MB) Acknowledgements The 3D MPII Cooking pose challenge data was recorded with a camera system from 4D View Solutions . Help & Contact [...] to allow for robust 3D pose estimation. We evaluate our multi-view pictorial structures approach on the HumanEva-I and MPII Cooking datasets. In comparison to related work for 3D pose estimation our approach
Interests Computer Vision, Object recognition Machine learning, Statistical decision theory Education Ph. D. student in Computer Science at the Max-Planck-Institut für Informatik and the Universität des Saarlandes [...] Sandanski Strumica, Macedonia Research Projects Addressing scalability in object recognition Teaching 3D Geometry to Deformable Part Models Publications See list of publications Zeynep Akata Stephan Alaniz
request] Software Semantic relatedness from Language resource For now see our previous release at www.d2.mpi-inf.mpg.de/nlp4vision. We will shortly add an updated version. Large Scale Learning In our recent [...] ( training , validation , test ) rgSift ( training , validation ) Groundtruth labels groundtruth (0.3 MB) zero shot class split known (800) unkown (200) Known Issues black-white images as we use rgSift
city of Washington D.C., which is the capital of the United States." then the goal is to extract the following pairs: instanceOf Mickey M. Mouse president Washington D.C. city Washington D.C. captial This [...] listed in the examples and a "wrong" birthdate is a counterexample. How LEILA works LEILA works in 3 phases: It finds all sentences in which an example pair appears. It collects the pattern in which the [...] Javatools K2 Know2Look Le Monde LEILA NAGA patty PATTY PRAVDA PROSPERA Quantity Search Qsearch QuTE QL RDF-3X RuLES SOFIE STICS TimeSEA UWN Watermarking YAGO Overview Demo Downloads Statistics Publications Linking
